← All models
★ FeaturedBalanced — strong quality at a mid priceOpen Weights
DeepSeek V3.2 Pricing
DeepSeek · deepseek-v3-2
Input / 1M tokens
$0.229
Output / 1M tokens
$0.343
Context window
131,072 tokens
≈ 175 pages of text
Max output
64k tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0004
1,000 requests / month$0.4118/mo10,000 requests / month$4.12/mo100,000 requests / month$41.18/moEstimate your own workloadOpens the calculator with DeepSeek V3.2 preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Extremely competitive coding and reasoning benchmarks at a fraction of commercial-API pricing — strong default for cost-sensitive batch workloads.
The business tradeoff
Open-weight hosting means latency and uptime vary by inference provider (DeepInfra, Fireworks, etc.) — pin a provider or add fallbacks for production SLAs.
Cheaper from DeepSeek
Head-to-head
Vendor list rates, as of Jun 15, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.